© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73573
    Prev
    Next
    INDEX
    Explanations

    Arkansas

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is specifically detecting occurrences of the word “Arkansas.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    -3.31
    d
    -3.17
    )
    -3.14
    We
    -3.08
    All
    -2.91
    ’
    -2.81
    0
    -2.61
    he
    -2.52
    ii
    -2.47
    4
    -2.45
    POSITIVE LOGITS
    髏
    2.64
    ꯴
    2.55
    妧
    2.53
    锨
    2.50
     berühm
    2.45
    神色
    2.45
    逦
    2.42
     ujedno
    2.39
    ’)
    2.38
    AutoresizingMask
    2.36
    Activations Density 0.003%

    No Known Activations